Reliability-oriented optimization of composite drill pipes Using integrated finite element and reinforcement learning framework

Journal article

Rasheed, S., Saeidlou, S., Kraiem, N., Alamry, A., Mahariq, I. and Javidparvar, A.A. 2026. Reliability-oriented optimization of composite drill pipes Using integrated finite element and reinforcement learning framework. Polymer Composites. https://doi.org/10.1002/pc.70514

Publication dates
Authors	Rasheed, S., Saeidlou, S., Kraiem, N., Alamry, A., Mahariq, I. and Javidparvar, A.A.
Abstract	This study aimed to optimize the stacking sequence for composite pipes under normative drilling applications through an integrated Finite Element-Reinforcement Learning scheme. In this essence, finite element provides the reward required to train a Deep Neural Network that gradually learns how to minimize the damage experienced by the composite pipe and shifts toward an optimum selection of fiber orientation for all layers. The optimum layup design was then assessed in terms of how it could endure the operational loads. In this way, to understand how different loading scenarios affect the creation of damage within layers, three Machine-Learning algorithms, Random Forests, Gaussian Process Regression, and Adaptive Neuro-Fuzzy Inference System were developed and trained based on finite element simulations performed on a coarse grid of different combinations of operational loads. The best models were employed to enhance the data resolution and, hence, to plot first-ply failure envelopes and safe operational limits. Furthermore, delamination was analyzed, and it was shown that this phenomenon did not limit the applicability of the optimum pipe. Finally, to account for the variability in mechanical properties, critical loads were calculated based on a population of pipes with statistically distributed mechanical properties. It was shown that such variations in the properties can significantly affect the applicable loads, and stringent precautions should be taken. Appropriate safety factors were proposed based on a thorough analysis of the behavior of composite pipes through statistical studies rather than rules of thumb.
Keywords	Composite pipes; Reinforcement learning; Machine learning; Reliability analysis; Finite element analysis; Oil and gas drilling
Year	2026
Journal	Polymer Composites
Publisher	Wiley
ISSN	1548-0569
Digital Object Identifier (DOI)	https://doi.org/10.1002/pc.70514
Official URL	https://4spepublications.onlinelibrary.wiley.com/doi/10.1002/pc.70514
Related URL	https://Funder
Funder	King Khalid University
Online	22 Oct 2025
Publication process dates
Accepted	22 Sep 2025
Deposited	27 Oct 2025
Accepted author manuscript	License CC BY-NC 4.0 File Access Level Open
Output status	Published
References	1. Petroleum B. Statistical Review of World Energy 2021. BP Energy Outlook 2021. 2021;70:8-20. https://www.energyinst.org/statistical-review 2. Energy Institute Statistical Review of World Energy 2024.; 2024. https://www.energyinst.org/statistical-review 3. U.S. Eenergy Information Administration-Monthly Energy Review. Published online 2024. https://www.eia.gov/totalenergy/data/monthly/ 4. Ember - Yearly Electricity Data (2024). Published online 2024. https://ember-climate.org/data-catalogue/yearly-electricity-data/ 5. Figueirôa SF, Good GA, Peyerl D. History, Exploration & Exploitation of Oil and Gas. (Figueirôa SF, Good GA, Peyerl D, eds.). Springer International Publishing; 2019. doi:10.1007/978-3-030-13880-6 6. Horton ST. Drill String and Drill Collars. The University of Texas at Austin - Petroleum Extension Service; 1995. 7. Gatlin C. Petroleum Engineering: Drilling and Well Completions.; 1960. 8. Chen P. Drilling and Completion Engineering.; 2011. 9. Ma T, Chen P, Zhao J. Overview on vertical and directional drilling technologies for the exploration and exploitation of deep petroleum resources. Geomech Geophys Geo-Energy Geo-Resources. 2016;2(4):365-395. doi:10.1007/s40948-016-0038-y 10. Awad A, Musleh O, Bordet L, Baryshev D, Prim MT. Extreme extended reach drilling depths with ultra high torque drill pipe. In: Society of Petroleum Engineers - Abu Dhabi International Petroleum Exhibition and Conference 2020, ADIP 2020. SPE; 2020. doi:10.2118/203473-ms 11. Quadflieg E, Sperber A. Material Selection and Concept for the Drill String of the Continental Deep Drilling Project, KTB. Published online 1990:302-309. doi:10.1007/978-3-642-50143-2_29 12. Rafiee R, Arabian MN. Investigating long-term creep in a composite pipe subjected to transverse loading and aqueous condition. Polym Compos. 2023;44(8):4706-4718. doi:10.1002/pc.27434 13. Peng X, Yu H, Lian Z, et al. Material optimization of drill pipe in complex wellbore environments by comparing fatigue life and cost. Energy Reports. 2021;7:5420-5430. doi:10.1016/j.egyr.2021.08.135 14. Kepir Y, Gunoz A, Kara M. Nonpenetrating repeated impact effect to the damage behavior of prestressed glass/epoxy composite pipes. Polym Compos. 2022;43(8):5047-5058. doi:10.1002/pc.26777 15. Sun Z, Ma Y, Ma S, Xiong H, Chen B. Mechanical properties and corrosion resistance enhancement of 2024 aluminum alloy for drill pipe after heat treatment and Sr modification. Mater Today Commun. 2023;36:106805. doi:10.1016/j.mtcomm.2023.106805 16. Liu W, Li J, Zhong Y, Shi T, Zhang J, Li S. Failure analysis on aluminum alloy drill pipe with pits and parallel transverse cracks. Eng Fail Anal. 2022;131:105809. doi:10.1016/j.engfailanal.2021.105809 17. Liu W, Wang S, Bu J, Ding X. An analytical model for the progressive failure prediction of reinforced thermoplastic pipes under axial compression. Polym Compos. 2021;42(6):3011-3024. doi:10.1002/pc.26035 18. Sepetcioglu H, Demet SM, Bagci M. A comprehensive experimental study of enhanced solid particle erosive resistance on the inner/outer surface of graphene nanoplatelets modified basalt/epoxy composite pipe. Polym Compos. 2023;44(10):6944-6956. doi:10.1002/pc.27609 19. Maiti S, Islam MR, Uddin MA, Afroj S, Eichhorn SJ, Karim N. Sustainable Fiber-Reinforced Composites: A Review. Adv Sustain Syst. 2022;6(11). doi:10.1002/adsu.202200258 20. Oğuz ZA, Özbek Ö, Bozkurt ÖY, Erkliğ A. Investigation of the effects of hydrothermal aging on the crushing properties of carbon/epoxy fiber reinforced pipes. Polym Compos. Published online April 2025. doi:10.1002/pc.29884 21. Talreja R, Waas AM. Concepts and definitions related to mechanical behavior of fiber reinforced composite materials. Compos Sci Technol. 2022;217:109081. doi:10.1016/j.compscitech.2021.109081 22. Demirci MT, Şahin ÖS. Low-velocity impact response and inspection of damage propagation for basalt fiber reinforced filament wound pipes. Polym Compos. 2022;43(7):4626-4644. doi:10.1002/pc.26718 23. Yashas Gowda TG, Sanjay MR, Subrahmanya Bhat K, Madhu P, Senthamaraikannan P, Yogesha B. Polymer matrix-natural fiber composites: An overview. Pham D, ed. Cogent Eng. 2018;5(1):1446667. doi:10.1080/23311916.2018.1446667 24. Sherif G, Chukov D, Tcherdyntsev V, Torokhov V. Effect of formation route on the mechanical properties of the polyethersulfone composites reinforced with glass fibers. Polymers (Basel). 2019;11(8):1364. doi:10.3390/polym11081364 25. Hull D, Clyne TW. An Introduction to Composite Materials. Cambridge University Press; 1996. doi:10.1017/cbo9781139170130 26. Leslie JC. Development and Manufacture of Cost-Effective Composite Drill Pipe.; 2011. 27. Jiang K, Xie R, Yun H. Lightweight Drill Pipe Based on Composite Carbon Fiber Material. J Phys Conf Ser. 2020;1549(3):32113. doi:10.1088/1742-6596/1549/3/032113 28. Pillay S, Ning H, Barfknecht P, Carlisle K. Long fiber thermoplastic composite for offshore drilling application - Design and prototyping. Compos Part B Eng. 2020;200:108339. doi:10.1016/j.compositesb.2020.108339 29. Liu Q, Zhou B, Chen F, et al. Optimal design and nonlinear dynamic characteristics of titanium /steel drill pipe composite drill string for ultra-deep drilling. Sci Rep. 2023;13(1). doi:10.1038/s41598-023-47156-y 30. Bazaluk O, Velychkovych A, Ropyak L, Pashechko M, Pryhorovska T, Lozynskyi V. Influence of heavy weight drill pipe material and drill bit manufacturing errors on stress state of steel blades. Energies. 2021;14(14):4198. doi:10.3390/en14144198 31. Karim MA, Abdullah MZ, Deifalla AF, Azab M, Waqar A. An assessment of the processing parameters and application of fibre-reinforced polymers (FRPs) in the petroleum and natural gas industries: A review. Results Eng. 2023;18:101091. doi:10.1016/j.rineng.2023.101091 32. Abdulrahman J, Ebhota WS, Tabakov PY. Biopolymer Composite Materials in Oil and Gas Sector. Shaker K, ed. Int J Polym Sci. 2024;2024(1). doi:10.1155/2024/8584879 33. M. AA, Aseel A, Roy R, Sunil P. Predictive big data analytics for drilling downhole problems: A review. Energy Reports. 2023;9:5863-5876. doi:10.1016/j.egyr.2023.05.028 34. Lahmadi A, Terrissa L, Zerhouni N. A data-driven method for estimating the remaining useful life of a composite drill pipe. 2018 Int Conf Adv Syst Electr Technol IC_ASET 2018. Published online 2018:192-195. doi:10.1109/ASET.2018.8379857 35. Wong KJ, Gong XJ, Aivazzadeh S, Tamin MN. Tensile behaviour of anti-symmetric CFRP composite. Procedia Eng. 2011;10:1865-1870. doi:10.1016/j.proeng.2011.04.310 36. Gaurav A. Data-driven machine learning regression methods to predict the residual strength in FRP composites subjected to fatigue. Polym Compos. Published online February 2025. doi:10.1002/pc.29648 37. Zhang L, Yang L, Lai C, et al. Prediction of tensile strength of basalt continuous fiber from chemical composition using machine learning models. Polym Compos. 2023;44(10):6634-6645. doi:10.1002/pc.27585 38. Cabrera-Ríos M, Castro JM. The balance between durability, reliability, and affordability in structural composites manufacturing. Polym Compos. 2007;28(2):233-240. doi:10.1002/pc.20262 39. Su H, Wei Z, Deng K, An D, He Y. Performance optimization and reliability analysis of CFRP adhesive-rivet hybrid joint. Polym Compos. Published online February 2025. doi:10.1002/pc.29605 40. Zhang J, Zhang R, Zeng Y. A Probabilistic Model of the Unidirectional Tensile Strength of Fiber-Reinforced Polymers for Structural Design. Adv Civ Eng. 2021;2021. doi:10.1155/2021/8476784 41. Mendenhall W, Beaver RJ, Beaver BM. Introduction to Probability and Statistics. Cengage Learning; 2012.

Permalink -

https://repository.canterbury.ac.uk/item/9w604/reliability-oriented-optimization-of-composite-drill-pipes-using-integrated-finite-element-and-reinforcement-learning-framework

File access - Request a copy

Restricted files

Accepted author manuscript

Under embargo until 22 Oct 2026

47
total views
2
total downloads
5
views this month
0
downloads this month

Export as

Related outputs

Comprehensive investigation of prediction methods, applications, challenges, and factors affecting the thermo-physical behavior of nanofluids

Deng, X., Ali B.M.A., Jasim, D.J., Singh, N.S.S., Saeidlou, S., Ahmad, Z., Baghoolizadeh, M., Fazilati, M.A. and Sahramaneshi, H. 2026. Comprehensive investigation of prediction methods, applications, challenges, and factors affecting the thermo-physical behavior of nanofluids. International Journal of Thermal Sciences. 220 (110317). https://doi.org/10.1016/j.ijthermalsci.2025.110317

Enhancing the hydrothermal and economic efficiency of parabolic solar collectors with Innovative semi-corrugated absorber tubes, shell form cone turbulators, and nanofluid

Samad, S., Saeidlou, S., Khan, M. N., Alamry, A., Al-Harbi, L. M., Sharifpur, M. and Ghoushchi, S.P. 2025. Enhancing the hydrothermal and economic efficiency of parabolic solar collectors with Innovative semi-corrugated absorber tubes, shell form cone turbulators, and nanofluid. Case Studies in Thermal Engineering. 75 (107003). https://doi.org/10.1016/j.csite.2025.107003

Bayesian-optimized surface energy microstructure-informed model of active dissolution in CrMnFeCoNi high-entropy alloys

Chahlaoui, Y., Saeidlou, S., Al-Harbi, L. M., Alamry, A., Alshehery, S., Mahariq, I. and Javidparvar, A. A. 2025. Bayesian-optimized surface energy microstructure-informed model of active dissolution in CrMnFeCoNi high-entropy alloys. Materials Today Communications. 49 (113741). https://doi.org/10.1016/j.mtcomm.2025.113741

An investigation into the effects of various phase change materials on industrial electronic systems' cooling rates through experimentation based on a specific dimensionless number

Leng, Z., Basem, A., Al-Nussairi, A. K. J., Singh, N. S. S., Saeidlou, S., Al-Khafaji, M. O., Alizade, M., Yazdekhasti, A., Salahshour, S. and Baghaei, S. 2025. An investigation into the effects of various phase change materials on industrial electronic systems' cooling rates through experimentation based on a specific dimensionless number . International Communications in Heat and Mass Transfer. 169 (A), p. 109573. https://doi.org/10.1016/j.icheatmasstransfer.2025.109573

Influence of graphene nanoplate size and heat flux on nanofluid heat exchanger performance: A molecular dynamics approach

Yang, Z., Basem, A., Jasim, D.J., Singh, N.S.S., Saeidlou, S., Al-Bahrani, M., Sajadi, S.M., Salahshour, S. and Hasanabad, A.M. 2025. Influence of graphene nanoplate size and heat flux on nanofluid heat exchanger performance: A molecular dynamics approach. International Communications in Heat and Mass Transfer. 167 (109386). https://doi.org/10.1016/j.icheatmasstransfer.2025.109386

Investigating the effect of variable heat flux on buckling of carbon nanotubes using non-equilibrium molecular dynamics simulation

Hou, G., Al-Mussawi, W., Khidhir, D.M., Singh, N.S.S., Saeidlou, S., Al-Bahrani, M., Salahshour, S., Sajadi, S.M. and Hasanabad, A.M. 2025. Investigating the effect of variable heat flux on buckling of carbon nanotubes using non-equilibrium molecular dynamics simulation. International Communications in Heat and Mass Transfer. 167 (109300). https://doi.org/10.1016/j.icheatmasstransfer.2025.109300

Nonlocal dual-phase-lag thermoelastic damping in in-plane vibrations of rotating rectangular cross-sectional nanorings according to nonlocal elasticity theory

Gârleanu, G., Mahariq, I., Saeidlou, S., Dobrota, D. and Tajbakhsh, M.R. 2025. Nonlocal dual-phase-lag thermoelastic damping in in-plane vibrations of rotating rectangular cross-sectional nanorings according to nonlocal elasticity theory. Acta Mechanica. https://doi.org/10.1007/s00707-025-04426-2

Energy-economy analysis of a novel spiral channeled conical turbulator Inserted within the parabolic trough solar collector absorber tube

Samad, S., Saeidlou, S., Mahariq, I., Kraiem, N., Alamry, A., Hoskeri, P. and Ghoushchi, S.P. 2025. Energy-economy analysis of a novel spiral channeled conical turbulator Inserted within the parabolic trough solar collector absorber tube. Case Studies in Thermal Engineering. 73 (106462). https://doi.org/10.1016/j.csite.2025.106462

Effect of channel thickness on the particle diffusion and permeability of carbon nanotubes a membrane in reverse electrodialysis process using molecular dynamics simulation

Sun, S., Basem, A., Sawaran Singh, N., Al-Zahy, Y., Saeidlou, S., Muzammil, K., Salahshour, S., Sajadi, M. and Sahramaneshi, H. 2025. Effect of channel thickness on the particle diffusion and permeability of carbon nanotubes a membrane in reverse electrodialysis process using molecular dynamics simulation. International Communications in Heat and Mass Transfer. 166 (109155). https://doi.org/10.1016/j.icheatmasstransfer.2025.109155

Closing the gap in engineering education: A positive psychology approach to CDIO

Ghadiminia, N., Saeidlou, S. and Nortcliffe, A. 2025. Closing the gap in engineering education: A positive psychology approach to CDIO.

Using evolutionary algorithms and group method of data handling ANN for prediction of the viscosity MWCNT-ZnO /oil SAE 50 nano-lubricant

Liu, Z., Ali, A. B., Hussein, R. A., Singh, N. S. S., Al-Bahrani, M., Abdullaeva, B., Saeidlou, S., Salahshour, S. and Esmaeili, S. 2025. Using evolutionary algorithms and group method of data handling ANN for prediction of the viscosity MWCNT-ZnO /oil SAE 50 nano-lubricant. International Communications in Heat and Mass Transfer. 163, p. 108749. https://doi.org/10.1016/j.icheatmasstransfer.2025.108749

Cyber-physical system security for manufacturing industry 4.0 using LSTM-CNN parallel orchestration

Saeidlou, S., Ghadiminia, N. and Oti-Sarpong, K. 2025. Cyber-physical system security for manufacturing industry 4.0 using LSTM-CNN parallel orchestration. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3525520

An inspiration for all time: Pioneer Verena Holmes' impact on future engineering practice

Saeidlou, S., Nortcliffe, A., Ghadiminia, N. and Ishaq, R. 2024. An inspiration for all time: Pioneer Verena Holmes' impact on future engineering practice. International Multidisciplinary Research Journal. 3, pp. 19-30. https://doi.org/10.47722/imrj.2001.33

Integrating AI into engineering education: Leveraging CDIO for enhanced assessment

Saeidlou, S., Nortcliffe, A., Ghadiminia, N. and Imam, A. 2024. Integrating AI into engineering education: Leveraging CDIO for enhanced assessment.

Practice-based engineering design for next-generation of engineers: A CDIO-based approach

Saeidlou, S., Ghadiminia, N., Nortcliffe, A. and Lambert, S. 2023. Practice-based engineering design for next-generation of engineers: A CDIO-based approach. in: The 19th CDIO International Conference: Proceedings - Full Papers

A digital approach to health and safety management on-site: A silver lining of the COVID-19 pandemic

Ghadiminia, N. and Saeidlou, S. 2023. A digital approach to health and safety management on-site: A silver lining of the COVID-19 pandemic. in: Manu, P., Cheung, C., Yunusa-Kaltungo, A., Emuze, F., Abreu Saurin, T. and Hadikusumo, B. (ed.) Construction Safety, Health and Well-being in the COVID-19 Era Routledge, Taylor and Francis.

A construction cost estimation framework using DNN and validation unit

Saeidlou, S. and Ghadiminia, N. 2023. A construction cost estimation framework using DNN and validation unit. Building Research & Information. 51 (3), pp. 241-368. https://doi.org/10.1080/09613218.2023.2196388

A hybrid clustering method based on the several diverse basic clustering and meta-clustering aggregation technique

Zhou, Bing, Lu, Bei and Saeidlou, Salman 2022. A hybrid clustering method based on the several diverse basic clustering and meta-clustering aggregation technique. Cybernetics and Systems. 55 (1), pp. 1-27. https://doi.org/10.1080/01969722.2022.2110682